10+ hours of podcasts, in 5 minutes.
6 quotes from 1 episode on Latent Space, each with a timestamped link to the source.
Kyle Daigle states that AI agents break traditional models for trusting and verifying software. Organizations lose established approval methods when one agent writes code and a second agent reviews the work.
Development environments face a complete shift when agents generate 80% of pull requests.
“…what does a pull request look like when 80% of your PRs are just coming from your agents and not from other devs you know.”
From GitHub CEO: AI Agents Just Broke Your Codebase Trust Model
Securing a platform creates a unique problem because every change disrupts the workflows of existing users.
“But like it is a unique challenge in that every move that we make to make it more secure will break a lot of people.”
From GitHub CEO: AI Agents Just Broke Your Codebase Trust Model
Engineering organizations currently rely on a developer's seniority or reputation to approve work. Kyle Daigle points out that this human-centric system changes when one agent writes the code and a second agent reviews it.
“The reason why there's not a single answer is ultimately we're trying to codify trust. We're trying to say like okay if Shawn reviews this, I'm going to trust it because you're Sean or you're the senior dev or you're the whatever.”
From GitHub CEO: AI Agents Just Broke Your Codebase Trust Model
“And right now when we are working in a flow where an agent writes code and another agent reviews code and then Kyle goes and looks at it, the trust is kind of diffuse…”
From GitHub CEO: AI Agents Just Broke Your Codebase Trust Model
Leaders use AI tools to build small data manipulation applications and stay close to technical tasks. Building functional systems provides a distinct upside for developers stepping into management roles.
“I think what you see there is me like really getting back to coding thanks to AI…”
“…make it look humanly bad and you know like and build a little app to like manipulate the data I think is part of like that upside for devs that are now in leadership roles.”
How we attribute quotes. Every quote was matched against the episode transcript, so the words and the timestamp are real (we trim filler words like "um", nothing else). The name comes from our written summary of the episode. YouTube gives us no voice-by-voice transcript, so open the timestamp to hear who is talking. See a wrong name? Tell us and we fix or remove it.
10+ hours of podcasts, distilled into one 5-minute read. Free, every Sunday morning.
One email a week. Unsubscribe with one click.